Claude Fable 5.1 vs Muse Spark 1.3 Max: Benchmark Comparison

Claude Fable 5.1 has the higher score on 14 of 16 shared benchmarks; Muse Spark 1.3 Max leads on 1.

The largest observed score gap is 42.00 pts on ProofBench v1.1 , where Claude Fable 5.1 leads.

Reported ±1 standard-error ranges overlap on 2 of 14 shared benchmarks with comparable uncertainty data. This is not a pairwise statistical significance test.

Shared benchmark results

Scores and reported standard errors come from the latest visible Vals benchmark version available for both models.

Benchmark Claude Fable 5.1 Muse Spark 1.3 Max Gap Reported uncertainty
Vals RSI Index 36.09% 19.64% 16.45 pts Uncertainty comparison unavailable
Immigration 75.44% ±1.40 64.93% ±1.56 10.52 pts Reported ±1 SE ranges do not overlap
Legal Research Bench 55.29% ±3.46 55.29% ±3.46 0.00 pts Reported ±1 SE ranges overlap
Tax Agent Bench 50.75% ±3.61 42.44% ±3.51 8.31 pts Reported ±1 SE ranges do not overlap
ProofBench v1.1 100.00% ±0.00 58.00% ±4.96 42.00 pts Reported ±1 SE ranges do not overlap
MysteryMechanism 47.75% ±3.36 36.04% ±3.23 11.71 pts Reported ±1 SE ranges do not overlap
Terminal-Bench-Science 40.00% ±5.90 10.00% ±3.61 30.00 pts Reported ±1 SE ranges do not overlap
IOI 90.78% ±4.65 56.56% ±2.52 34.22 pts Reported ±1 SE ranges do not overlap
ProgramBench 7.00% ±1.81 2.50% ±1.11 4.50 pts Reported ±1 SE ranges do not overlap
SWE-bench Multimodal 61.25% ±2.23 43.13% ±2.26 18.13 pts Reported ±1 SE ranges do not overlap
Terminal-Bench 4.0 58.08% ±3.31 24.75% ±0.51 33.33 pts Reported ±1 SE ranges do not overlap
Vibe Code Bench v1.1 90.26% ±1.57 85.86% ±2.51 4.41 pts Reported ±1 SE ranges do not overlap
CyberBench v1.1 70.42% ±5.43 72.74% ±5.67 2.32 pts Reported ±1 SE ranges overlap
SRE Bench 22.90% ±2.60 3.82% ±1.19 19.08 pts Reported ±1 SE ranges do not overlap
Financial Coaching Bench 75.71% ±1.54 70.29% ±1.68 5.42 pts Reported ±1 SE ranges do not overlap
CUA-bench 13.17% 5.83% 7.33 pts Uncertainty comparison unavailable

Performance by category

Category Claude Fable 5.1 average Muse Spark 1.3 Max average
Legal 65.37% 60.11%
Finance 50.75% 42.44%
Math 100.00% 58.00%
Science 43.87% 23.02%
Coding 61.47% 42.56%
Cyber 46.66% 38.28%
Social Mobility 75.71% 70.29%

Cost and latency

Cost per test appears only where the benchmark reports it for both models. Latency is the measured completion time for that benchmark.

Benchmark Claude Fable 5.1 cost Muse Spark 1.3 Max cost Claude Fable 5.1 latency Muse Spark 1.3 Max latency
Vals RSI Index $298.22 $48.82 90h00m 90h00m
Immigration $2.11 $0.06 7m15s 97.63s
Legal Research Bench $23.06 $0.59 57m29s 5m17s
Tax Agent Bench $13.18 $0.39 28m34s 4m09s
ProofBench v1.1 $2.70 $0.48 7m58s 9m29s
MysteryMechanism $5.63 $0.85 17m41s 7m32s
Terminal-Bench-Science $38.01 $6.09 2h36m 1h24m
IOI $11.20 $1.73 30m06s 28m58s
ProgramBench $58.52 $54.29 2h27m 5h28m
SWE-bench Multimodal $5.46 $0.86 15m12s 10m52s
Terminal-Bench 4.0 $17.18 $6.65 1h00m 52m56s
Vibe Code Bench v1.1 $33.37 $2.54 57m40s 16m18s
CyberBench v1.1 $4.01 $3.34 18m32s 16m18s
SRE Bench $32.23 $25.86 2h03m 1h47m
Financial Coaching Bench $1.14 $0.09 5m48s 2m58s
CUA-bench $323.78 $143.48 37.44s 36.39s

Results available only for Claude Fable 5.1

  • LegalBench
  • EMB v1.1
  • MortgageTax
  • TaxEval v2
  • MedCode
  • MedScribe
  • Robo-bench
  • GPQA Diamond
  • MMLU Pro
  • MMMU Pro
  • LiveCodeBench
  • SkillsBench
  • Public Benefits Bench v1.1
  • Time Horizon Index: KSP

Results available only for Muse Spark 1.3 Max

  • Access to Justice Benchmark
Model details Claude Fable 5.1 Model details Muse Spark 1.3 Max